Loading...
Loading...
Found 57 Skills
Guides research engineering and science on LLM tokens—hypotheses about context use, tokenization, compression, and inference efficiency; rigorous benchmarks (tokens per task, quality–cost Pareto); ablation design; instrumentation and reproducible logs; and research memos that inform product decisions. Use when designing token-efficiency experiments, measuring context utilization, comparing compression or routing methods, analyzing tokenizer effects, or writing technical reports on token/cost trade-offs—not for phased cost roadmaps and owners (ai-token-improvement-plan-engineer), production context pipeline implementation (ai-context-engineer), single-prompt edits (prompt-engineer), general non-token AI research (ai-researcher), or shipping features (ai-engineer).
CLI interface for Perplexity AI. Perform AI-powered searches, queries, and research directly from terminal. Use when user mentions Perplexity, AI search, web research, or needs to query AI models like GPT, Claude, Grok, Gemini. Commands: query.
Use when the user is doing AI/ML work in a scientific domain — biology, chemistry, physics, astronomy, climate, genomics, materials science, medicine, ecology, energy, conservation, engineering, mathematics, scientific reasoning, drug discovery, protein design, weather modeling, theorem proving, single-cell, PDE solving, or anything similar. Hugging Science (huggingscience.co) is a curated catalog of scientific datasets, models, blog posts, and interactive Spaces; the `hugging-science` org on Hugging Face hosts community datasets, models, and demo Spaces. This skill helps you discover the right resource AND actually use it — loading datasets via `datasets`, running models via `transformers` or the HF Inference API, calling Spaces like BoltzGen via `gradio_client`, and citing blog posts for methodology. Trigger this skill whenever a user mentions a scientific ML task, asks for "a dataset/model for X" where X is a scientific topic, wants to fine-tune on scientific data, asks about protein / molecule / genome / climate / materials / astronomy / pathology / weather ML, or needs AI tools for research — even if they never say "Hugging Science" explicitly. The catalog is purpose-built for LLM agents (it ships an `llms-full.txt`); prefer it over generic web search for these tasks.
Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.
Finalize an accepted ML or AI paper for camera-ready submission after reviews, rebuttal, and acceptance. Use this skill whenever the user has an accepted paper, camera-ready deadline, final revision, acceptance email, meta-review, rebuttal promises, author-response commitments, de-anonymization tasks, supplement updates, code links, acknowledgements, final LaTeX checks, or needs to ensure the accepted paper's claims, figures, references, and artifacts are consistent before final submission.
Enables Claude to conduct comprehensive research using Gemini Deep Research for in-depth analysis and reports
Decompose research ideas into atomic, self-contained concepts with bidirectional math-code mapping. For each concept, extract the math formula from papers and find code implementations. Use for complex system papers requiring formal grounding.
Technical research methodology using Context7, Exa, and Sequential Thinking for documentation, best practices, and complex investigations.
Use Chrome DevTools Protocol to allow the AI to "ask Gemini" or "research with Gemini" directly. This uses the user's logged-in Chrome session, bypassing API limits and leveraging the web interface's reasoning capabilities.
Manages persistent research memory across ideation and experimentation cycles. Maintains two stores: Ideation Memory M_I (feasible/unsuccessful directions) and Experimentation Memory M_E (reusable strategies for data processing, model training, architecture, debugging). Three evolution mechanisms: IDE (after idea-tournament), IVE (after experiment failure — classifies failures as implementation vs fundamental), ESE (after experiment success — extracts reusable strategies). Use when: updating memory after completing idea tournaments or experiment pipelines, classifying why a method failed (implementation vs fundamental failure), starting a new research cycle needing prior knowledge, user mentions 'update memory', 'classify failure', 'what worked before', 'research history', 'evolution'. Do NOT use for running experiments (use experiment-pipeline), debugging experiment code (use experiment-craft), or generating ideas (use idea-tournament).
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
NotebookLM CLI wrapper via `python3 {baseDir}/scripts/notebooklm.py` (backed by notebooklm-py). Use for auth, notebooks, chat, sources, notes, sharing, research, and artifact generation/download.